Multi-agent assignment via state augmented reinforcement learning

Leopoldo Agorio, Sean Van Alen, Miguel Calvo-Fullana, Santiago Paternain, Juan Andrés Bazerque
Proceedings of the 6th Annual Learning for Dynamics & Control Conference, PMLR 242:1202-1213, 2024.

Abstract

We address the conflicting requirements of a multi-agent assignment problem through constrained reinforcement learning, emphasizing the inadequacy of standard regularization techniques for this purpose. Instead, we recur to a state augmentation approach in which the oscillation of dual variables is exploited by agents to alternate between tasks. In addition, we coordinate the actions of the multiple agents acting on their local states through these multipliers, which are gossiped through a communication network, eliminating the need to access other agent states. By these means, we propose a distributed multi-agent assignment protocol with theoretical feasibility guarantees that we corroborate in a monitoring numerical experiment.

Cite this Paper

BibTeX
@InProceedings{pmlr-v242-agorio24a, title = {Multi-agent assignment via state augmented reinforcement learning}, author = {Agorio, Leopoldo and Alen, Sean Van and Calvo-Fullana, Miguel and Paternain, Santiago and Bazerque, Juan Andr\'{e}s}, booktitle = {Proceedings of the 6th Annual Learning for Dynamics & Control Conference}, pages = {1202--1213}, year = {2024}, editor = {Abate, Alessandro and Cannon, Mark and Margellos, Kostas and Papachristodoulou, Antonis}, volume = {242}, series = {Proceedings of Machine Learning Research}, month = {15--17 Jul}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v242/agorio24a/agorio24a.pdf}, url = {https://proceedings.mlr.press/v242/agorio24a.html}, abstract = {We address the conflicting requirements of a multi-agent assignment problem through constrained reinforcement learning, emphasizing the inadequacy of standard regularization techniques for this purpose. Instead, we recur to a state augmentation approach in which the oscillation of dual variables is exploited by agents to alternate between tasks. In addition, we coordinate the actions of the multiple agents acting on their local states through these multipliers, which are gossiped through a communication network, eliminating the need to access other agent states. By these means, we propose a distributed multi-agent assignment protocol with theoretical feasibility guarantees that we corroborate in a monitoring numerical experiment.} }
Endnote
%0 Conference Paper %T Multi-agent assignment via state augmented reinforcement learning %A Leopoldo Agorio %A Sean Van Alen %A Miguel Calvo-Fullana %A Santiago Paternain %A Juan Andrés Bazerque %B Proceedings of the 6th Annual Learning for Dynamics & Control Conference %C Proceedings of Machine Learning Research %D 2024 %E Alessandro Abate %E Mark Cannon %E Kostas Margellos %E Antonis Papachristodoulou %F pmlr-v242-agorio24a %I PMLR %P 1202--1213 %U https://proceedings.mlr.press/v242/agorio24a.html %V 242 %X We address the conflicting requirements of a multi-agent assignment problem through constrained reinforcement learning, emphasizing the inadequacy of standard regularization techniques for this purpose. Instead, we recur to a state augmentation approach in which the oscillation of dual variables is exploited by agents to alternate between tasks. In addition, we coordinate the actions of the multiple agents acting on their local states through these multipliers, which are gossiped through a communication network, eliminating the need to access other agent states. By these means, we propose a distributed multi-agent assignment protocol with theoretical feasibility guarantees that we corroborate in a monitoring numerical experiment.
APA
Agorio, L., Alen, S.V., Calvo-Fullana, M., Paternain, S. & Bazerque, J.A.. (2024). Multi-agent assignment via state augmented reinforcement learning. Proceedings of the 6th Annual Learning for Dynamics & Control Conference, in Proceedings of Machine Learning Research 242:1202-1213 Available from https://proceedings.mlr.press/v242/agorio24a.html.

Related Material